Raw QPP-RNG randomness via system jitter across platforms: a NIST SP 800-90B evaluation
Bibliographic record
Abstract
High-quality randomness is fundamental to the security of modern cryptographic systems. We present QPP-RNG, a true random number generator (TRNG) that harvests entropy from diverse system-level jitters-including CPU pipeline timing divergences, DRAM refresh cycle perturbations, cache miss-driven memory access latencies, and other subtle hardware and operating system-induced fluctuations. QPP-RNG's core mechanism measures the elapsed time of randomized array sorting operations-where each Fisher-Yates shuffle is infinitesimally perturbed by these microscopic jitters-and amplifies these timing variations into cryptographically strong randomness through a quantum permutation pad (QPP) architecture, all achievable on commodity hardware. The raw output of QPP-RNG underwent rigorous evaluation for independent and identically distributed (IID) behavior using the NIST SP 800-90B IID test suite, alongside the comprehensive NIST SP 800-22 and ENT statistical test batteries. Across a range of platforms, including Windows, macOS, and Raspberry Pi, QPP-RNG consistently achieved high IID min-entropy between [Formula: see text] and [Formula: see text] bits/byte. It passed all NIST SP 800-90B IID tests with [Formula: see text]-values significantly above the [Formula: see text] threshold, confirming that its generated randomness is statistically indistinguishable from ideal IID sources derived directly from system jitter. Cross-platform analyses spanning x86_64 and ARM64 architectures further demonstrate that the extracted jitter fingerprint-and consequently the generated randomness-exhibits remarkable statistical consistency, irrespective of the underlying hardware or operating system. QPP-RNG's entropy density compares favorably with leading commercial entropy sources. It matches or slightly exceeds the NIST IID-certified min-entropy of ID Quantique's Quantis QRNG (7.8744 bits/byte), and significantly outperforms both Red Hat's CPU Time Jitter RNG (7.4528 bits/byte) and Quside's PCIe One quantum entropy source (6.5136 bits/byte). Even against specialized hardware RNGs like Microchip's ECC608 (4.0568 bits/byte), QPP-RNG demonstrates superior performance using only general-purpose processors. By effectively transforming otherwise discarded system noise into a reliable and high-quality entropy stream, QPP-RNG establishes a novel paradigm for embedded security, providing a robust entropy source on general-purpose devices without specialized hardware. This makes it especially well-suited for resource-constrained Internet of Things (IoT) and edge computing applications where strong entropy sources are paramount.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".